作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2009, Vol. 35 ›› Issue (11): 181-183. doi: 10.3969/j.issn.1000-3428.2009.11.062

• 人工智能及识别技术 • 上一篇    下一篇

人脸识别率与图像分辨率关系的比较分析

丁晓莲1,周激流2,李晓华2,吴 朋2   

  1. (1. 四川大学电子信息学院,成都 610064;2. 四川大学计算机学院,成都 610064)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-06-05 发布日期:2009-06-05

Comparative Analysis of Relation Between Face Recognition Rate and Image Resolution

DING Xiao-lian1, ZHOU Ji-liu2, LI Xiao-hua2, WU Peng2   

  1. (1. School of Electronic & Information, Sichuan University, Chengdu 610064; 2. College of Computer, Sichuan University, Chengdu 610064)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-06-05 Published:2009-06-05

摘要: 为在低分辨率图像中提高人脸识别率,从实际应用角度出发,分析研究图像分辨率与人脸识别率间的关系,在此基础上,采用主成分分析方法,对3种数据库中具有不同分辨率的人脸图像进行识别。仿真实验结果表明,该方法能在人脸图像分辨率较低的情况下获得与高分辨率图像基本一致的识别效果,且同时兼顾识别率及识别效率。

关键词: 人脸识别, 主成分分析, 人脸图像分辨率, 识别率

Abstract: In order to promote the face recognition rate in low-resolution image, from the point of view of practical applications, the relationship between image resolution and face recognition rate is studied, and on basis of which, some face images with different resolutions in three database are recognized by using Principle Component Analysis(PCA) method. Simulation experimental results show this method achieves the fact that the recognition performance under low face image resolution is almost the same as that under high one, and both recognition rate and efficiency are considered.

Key words: face recognition, Principle Component Analysis(PCA), face image resolution, recognition rate

中图分类号: